Memory Cell Soft Metrics for Multi-Word-Line ECC Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in accurately decoding data due to disturbances from neighboring memory cells, which can lead to errors, especially when threshold voltages overlap, and current methods require high computational complexity to consider disturbances from multiple neighbor word lines.
Innovation Solution
A memory controller calculates separate soft metrics for each neighbor word line and combines them to produce a combined soft metric, which takes into account disturbances from multiple neighbor word lines, reducing complexity and improving decoding performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If methods consider interference from neighbor memory cells in multiple word lines, then decoding accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the interference compensation process by calculating separate soft metrics for each neighbor word line independently, then combining them. This divides the complex multi-word line interference problem into manageable per-word-line components, reducing overall computational complexity while maintaining decoding accuracy
Solution Approach 2:
The patent applies partial action by focusing interference compensation only on the most significant neighbor word lines (typically immediate neighbors) rather than all possible word lines. This selective approach provides sufficient decoding accuracy improvement without the prohibitive complexity of considering every possible interfering cell
2Reliability
If soft metrics are calculated for each neighbor word line separately and combined, then decoding reliability is improved, but processing time increases
Solution Approach 1:
The patent segments the soft metric calculation into independent per-word-line operations that can be executed in parallel. By calculating soft metrics for each neighbor word line separately and then combining them through simple addition, the processing pipeline is optimized to reduce overall processing time while maintaining high decoding reliability
Solution Approach 2:
The patent merges the individual soft metrics from multiple neighbor word lines through a simple additive combination. This merging operation is computationally efficient compared to more complex integration methods, thereby reducing processing time while preserving the reliability benefits of considering multiple neighbor word lines
Data Source
AI summary
A memory controller includes an interface and a processor. The interface communicates with memory cells organized in multiple Word Lines (WLs). The processor is configured to read a Code Word (CW) of an Error Correction Code (ECC) from a group of multiple memory cells belonging to a target WL, to calculate for a given memory cell (i) a first soft metric, depending on a first threshold voltage of a first neighbor memory cell in a first WL neighboring the target WL, and (ii) a second soft metric, depending on a second threshold voltage of a second neighbor memory cell in a second WL neighboring the target WL, to calculate a combined soft metric based on both the first and second soft metrics and assign the combined soft metric to the given memory cell, and to decode the CW based on the combined soft metric, to produce a decoded CW.